© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12876
    Prev
    Next
    INDEX
    Explanations

    a mix of numbers and various short, common, English words

    oai_token-act-pair · gemini-2.0-flash

    various types of data or programming elements

    np_token-act-pair-logits · gpt-4o-mini

    3

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.65
    "]="
    -0.62
    脚注の使い方
    -0.62
    atche
    -0.60
    CLAIMER
    -0.60
    //};
    -0.58
     насељу
    -0.57
     الرياضيه
    -0.57
    DrawerToggle
    -0.55
    ']);
    -0.54
    POSITIVE LOGITS
    rd
    0.63
    UnsafeEnabled
    0.49
    nto
    0.47
     فريبيس
    0.46
    fromnode
    0.46
     confezione
    0.46
    Jsp
    0.45
     comigo
    0.45
    amento
    0.44
    M
    0.43
    Activations Density 24.949%

    No Known Activations